lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20090720122417.GR5638@redhat.com>
Date:	Mon, 20 Jul 2009 15:24:17 +0300
From:	Gleb Natapov <gleb@...hat.com>
To:	Ingo Molnar <mingo@...e.hu>
Cc:	Suresh Siddha <suresh.b.siddha@...el.com>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	Sheng Yang <sheng@...ux.intel.com>,
	"kvm@...r.kernel.org" <kvm@...r.kernel.org>,
	"avi@...hat.com" <avi@...hat.com>
Subject: [PATCH] enable x2APIC without interrupt remapping under KVM

KVM would like to provide x2APIC interface to a guest without emulating
interrupt remapping device. The reason KVM prefers guest to use x2APIC
is that x2APIC interface is better virtualizable and provides better
performance than mmio xAPIC interface:

- msr exits are faster than mmio (no page table walk, emulation)
- no need to read back ICR to look at the busy bit
- one 64 bit ICR write instead of two 32 bit writes
- shared code with the Hyper-V paravirt interface

Included patch changes x2APIC enabling logic to enable it even if IR
initialization failed, but kernel runs under KVM and no apic id is
greater than 255 (if there is one spec requires BIOS to move to x2apic
mode before starting an OS).

Signed-off-by: Gleb Natapov <gleb@...hat.com>
Acked-by: Suresh Siddha <suresh.b.siddha@...el.com>
---

This is based on x86 tree commit ff78d570fae with Ingo comments
addressed (comment formatting, print error on alloc failure, shorter
error messages).

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 0a1c283..a79e8a9 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -49,6 +49,7 @@
 #include <asm/mtrr.h>
 #include <asm/smp.h>
 #include <asm/mce.h>
+#include <asm/kvm_para.h>
 
 unsigned int num_processors;
 
@@ -1361,52 +1362,76 @@ void enable_x2apic(void)
 }
 #endif /* CONFIG_X86_X2APIC */
 
-void __init enable_IR_x2apic(void)
+int __init enable_IR(void)
 {
 #ifdef CONFIG_INTR_REMAP
 	int ret;
-	unsigned long flags;
-	struct IO_APIC_route_entry **ioapic_entries = NULL;
 
 	ret = dmar_table_init();
 	if (ret) {
 		pr_debug("dmar_table_init() failed with %d:\n", ret);
-		goto ir_failed;
+		return 0;
 	}
 
 	if (!intr_remapping_supported()) {
 		pr_debug("intr-remapping not supported\n");
-		goto ir_failed;
+		return 0;
 	}
 
-
 	if (!x2apic_preenabled && skip_ioapic_setup) {
 		pr_info("Skipped enabling intr-remap because of skipping "
 			"io-apic setup\n");
-		return;
+		return 0;
 	}
 
+	if (enable_intr_remapping(x2apic_supported()))
+		return 0;
+
+	pr_info("Enabled Interrupt-remapping\n");
+
+	return 1;
+
+#endif
+	return 0;
+}
+
+void __init enable_IR_x2apic(void)
+{
+	unsigned long flags;
+	struct IO_APIC_route_entry **ioapic_entries = NULL;
+	int ret, x2apic_enabled = 0;
+
 	ioapic_entries = alloc_ioapic_entries();
 	if (!ioapic_entries) {
-		pr_info("Allocate ioapic_entries failed: %d\n", ret);
-		goto end;
+		pr_err("Allocate ioapic_entries failed\n");
+		goto out;
 	}
 
 	ret = save_IO_APIC_setup(ioapic_entries);
 	if (ret) {
 		pr_info("Saving IO-APIC state failed: %d\n", ret);
-		goto end;
+		goto out;
 	}
 
 	local_irq_save(flags);
-	mask_IO_APIC_setup(ioapic_entries);
 	mask_8259A();
+	mask_IO_APIC_setup(ioapic_entries);
 
-	ret = enable_intr_remapping(x2apic_supported());
-	if (ret)
-		goto end_restore;
+	ret = enable_IR();
+	if (!ret) {
+		/* IR is required if there is APIC ID > 255 even when running
+		 * under KVM
+		 */
+		if (max_physical_apicid > 255 || !kvm_para_available())
+			goto nox2apic;
+		/*
+		 * without IR all CPUs can be addressed by IOAPIC/MSI
+		 * only in physical mode
+		 */
+		x2apic_phys = 1;
+	}
 
-	pr_info("Enabled Interrupt-remapping\n");
+	x2apic_enabled = 1;
 
 	if (x2apic_supported() && !x2apic_mode) {
 		x2apic_mode = 1;
@@ -1414,41 +1439,25 @@ void __init enable_IR_x2apic(void)
 		pr_info("Enabled x2apic\n");
 	}
 
-end_restore:
-	if (ret)
-		/*
-		 * IR enabling failed
-		 */
+nox2apic:
+	if (!ret) /* IR enabling failed */
 		restore_IO_APIC_setup(ioapic_entries);
-
 	unmask_8259A();
 	local_irq_restore(flags);
 
-end:
+out:
 	if (ioapic_entries)
 		free_ioapic_entries(ioapic_entries);
 
-	if (!ret)
+	if (x2apic_enabled)
 		return;
 
-ir_failed:
 	if (x2apic_preenabled)
-		panic("x2apic enabled by bios. But IR enabling failed");
+		panic("x2apic: enabled by BIOS but kernel init failed.");
 	else if (cpu_has_x2apic)
-		pr_info("Not enabling x2apic,Intr-remapping\n");
-#else
-	if (!cpu_has_x2apic)
-		return;
-
-	if (x2apic_preenabled)
-		panic("x2apic enabled prior OS handover,"
-		      " enable CONFIG_X86_X2APIC, CONFIG_INTR_REMAP");
-#endif
-
-	return;
+		pr_info("Not enabling x2apic, Intr-remapping init failed.\n");
 }
 
-
 #ifdef CONFIG_X86_64
 /*
  * Detect and enable local APICs on non-SMP boards.
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index bc3e880..f3b1037 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -50,11 +50,11 @@ static struct apic *apic_probe[] __initdata = {
 void __init default_setup_apic_routing(void)
 {
 #ifdef CONFIG_X86_X2APIC
-	if (x2apic_mode && (apic != &apic_x2apic_phys &&
+	if (x2apic_mode
 #ifdef CONFIG_X86_UV
-		       apic != &apic_x2apic_uv_x &&
+		       && apic != &apic_x2apic_uv_x
 #endif
-		       apic != &apic_x2apic_cluster)) {
+		       ) {
 		if (x2apic_phys)
 			apic = &apic_x2apic_phys;
 		else
--
			Gleb.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ